Parallel Iterative Solvers with Localized ILU Preconditioning for Unstructured Grids on Workstation Clusters

Incomplete Lower-Upper (0) (ILU(O)) factorization is a very effective preconditioning method of iterative solvers for large-scale linear sparse systems in scientific and engineering computations. However, this method requires global data dependency, which is not ideal for parallel computations in which locality is of utmost importance. In this paper, the localized ILU(O) preconditioning method is implemented in various types of iterative solvers. This method provides data locality and good parallelization on each processor. The performance of the developed system was evaluated on a workstation cluster using MPI. In 1997, the Science and Technology Agency of Japan (STA) began a five-year project to develop the Earth Simulator. Both hardware and software for various types of global earth simulation are to be developed under this project. The present study was conducted as part of the research on software for solid earth simulation. This simulation code, named GeoFEM, solves crust deformation, mantle convect...